A Unified Framework for Dynamic Reward Shaping in Reinforcement Learning
Fouad Bahrpeyma
cs.AI, cs.LG
Submitted: 2026-08-08
Updated: 2026-08-11
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Reward Training Wheels: Adaptive Auxiliary Rewards for Robotics Reinforcement Learning
- Subgoal-based Reward Shaping to Improve Efficiency in Reinforcement Learning
- Potential-Based Intrinsic Motivation: Preserving Optimality With Complex, Non-Markovian Shaping Rewards
- Action-Dependent Optimality-Preserving Reward Shaping
- Adaptive Reward Design for Reinforcement Learning
- Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning
- Vision-Language Models as a Source of Rewards
- Automating Potential-based Reward Shaping with Vision Language Model Guidance
- Concrete Problems in AI Safety
- Constitutional AI: Harmlessness from AI Feedback
- Useful Policy Invariant Shaping from Arbitrary Advice
- Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity
- Comprehensive Overview of Reward Engineering and Shaping in Advancing Reinforcement Learning Applications
- SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement Learning
- InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
- Improving the Effectiveness of Potential-Based Reward Shaping in Reinforcement Learning
- Offline Reinforcement Learning with Imputed Rewards
- Training Language Models with Language Feedback
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems